diff --git a/Datasets/processingTXT.py b/Datasets/originals/processingTXT.py
similarity index 98%
rename from Datasets/processingTXT.py
rename to Datasets/originals/processingTXT.py
index 9fc9eca6509399be7b2d7015bce23c1e6ac201c0..cdcacc3f77a926e61dc6202727fd942b47b751ff 100644
--- a/Datasets/processingTXT.py
+++ b/Datasets/originals/processingTXT.py
@@ -11,9 +11,9 @@ import pandas as pd
def normalize_word(orig_word):
word = orig_word.lower()
- if (word is "["):
+ if (word == "["):
word = "("
- if (word is "]"):
+ if (word == "]"):
word = ")"
return word
diff --git a/SuperTagger/Datasets/m2.txt b/SuperTagger/Datasets/originals/m2.txt
similarity index 100%
rename from SuperTagger/Datasets/m2.txt
rename to SuperTagger/Datasets/originals/m2.txt
diff --git a/SuperTagger/Datasets/processingTXT.py b/SuperTagger/Datasets/originals/processingTXT.py
similarity index 100%
rename from SuperTagger/Datasets/processingTXT.py
rename to SuperTagger/Datasets/originals/processingTXT.py
diff --git a/find_config.py b/find_config.py
new file mode 100644
index 0000000000000000000000000000000000000000..42d5e19aeb43b42164f663261a0d1c9fd6e6b2bd
--- /dev/null
+++ b/find_config.py
@@ -0,0 +1,61 @@
+import configparser
+import re
+
+import torch
+
+from Linker.atom_map import atom_map_redux
+from Linker.utils_linker import get_GOAL, get_atoms_links_batch, get_atoms_batch
+from SuperTagger.SuperTagger.SuperTagger import SuperTagger
+from utils import read_csv_pgbar, pad_sequence
+
+
+def configurate(dataset, model_tagger, nb_sentences=1000000000):
+ print("#" * 20)
+ print("#" * 20)
+ print("Configuration with dataset\n")
+ config = configparser.ConfigParser()
+ config.read('Configuration/config.ini')
+
+ file_path_axiom_links = dataset
+ df_axiom_links = read_csv_pgbar(file_path_axiom_links, nb_sentences)
+
+ supertagger = SuperTagger()
+ supertagger.load_weights(model_tagger)
+ sentences_batch = df_axiom_links["X"].str.strip().tolist()
+ sentences_tokens, sentences_mask = supertagger.sent_tokenizer.fit_transform_tensors(sentences_batch)
+ max_len_sentence = 0
+ for sentence in sentences_tokens:
+ if len(sentence) > max_len_sentence:
+ max_len_sentence = len(sentence)
+ print("Configure parameter max len sentence to ", max_len_sentence)
+ config.set('DATASET_PARAMS', 'max_len_sentence', str(max_len_sentence))
+
+ atoms_batch, polarities, num_batch = get_GOAL(max_len_sentence, df_axiom_links)
+ max_atoms_in_sentence = 0
+ for sentence in atoms_batch:
+ if len(sentence) > max_atoms_in_sentence:
+ max_atoms_in_sentence = len(sentence)
+ print("Configure parameter max atoms in categories to", max_atoms_in_sentence)
+ config.set('DATASET_PARAMS', 'max_atoms_in_sentence', str(max_atoms_in_sentence))
+
+ atoms_polarity_batch = pad_sequence([torch.as_tensor(polarities[i], dtype=torch.bool) for i in range(len(polarities))],
+ max_len=max_atoms_in_sentence, padding_value=0)
+ pos_idx = [[torch.as_tensor([i for i, x in enumerate(sentence) if
+ bool(re.match(r"" + atom_type + "(_{1}\w+)?\Z", atoms_batch[s_idx][i]))
+ and atoms_polarity_batch[s_idx][i]])
+ for s_idx, sentence in enumerate(atoms_batch)]
+ for atom_type in list(atom_map_redux.keys())]
+ max_atoms_in_on_type = 0
+ for atoms_type_batch in pos_idx:
+ for sentence in atoms_type_batch:
+ length = sentence.size(0)
+ if length > max_atoms_in_on_type:
+ max_atoms_in_on_type = length
+ print("Configure parameter max atoms of one type in one sentence to", max_atoms_in_on_type)
+ config.set('DATASET_PARAMS', 'max_atoms_in_one_type', str(max_atoms_in_on_type * 2+2))
+
+ with open('Configuration/config.ini', 'w') as configfile: # save
+ config.write(configfile)
+
+ print("#" * 20)
+ print("#" * 20)
diff --git a/slurm.sh b/slurm.sh
new file mode 100644
index 0000000000000000000000000000000000000000..b2f521c72e4c0ffe8dafb66def0f8e398e12cac1
--- /dev/null
+++ b/slurm.sh
@@ -0,0 +1,13 @@
+#!/bin/sh
+#SBATCH --job-name=Deepgrail_Linker
+#SBATCH --partition=RTX6000Node
+#SBATCH --gres=gpu:1
+#SBATCH --mem=32000
+#SBATCH --gres-flags=enforce-binding
+#SBATCH --error="error_rtx1.err"
+#SBATCH --output="out_rtx1.out"
+
+module purge
+module load singularity/3.0.3
+
+srun singularity exec /logiciels/containerCollections/CUDA11/pytorch-NGC-21-03-py3.sif python "train_neuralproofnet.py"
diff --git a/train_neuralproofnet.py b/train_neuralproofnet.py
index daa6f651c783e10d7b909c8c839be603c1b9aad0..ce393adfa39c6bfa8b5b52e3d3888453ec892e52 100644
--- a/train_neuralproofnet.py
+++ b/train_neuralproofnet.py
@@ -16,7 +16,7 @@ print("#" * 20)
print("#" * 20)
model_tagger = "models/flaubert_super_98_V2_50e.pt"
neural_proof_net = NeuralProofNet(model_tagger)
-neural_proof_net.train_neuralproofnet(df_axiom_links, validation_rate=0.1, epochs=5, batch_size=16,
+neural_proof_net.train_neuralproofnet(df_axiom_links, validation_rate=0.1, epochs=25, pretrain_linker_epochs=20, batch_size=16,
checkpoint=True, tensorboard=True)
print("#" * 20)
print("#" * 20)
diff --git a/train_supertagger.py b/train_supertagger.py
index edba002387343ab034e4a1bc69488f5a28b1c2a8..2ea2aee9ae9e23fd5cc2091d51aa0afff0e3a5b8 100644
--- a/train_supertagger.py
+++ b/train_supertagger.py
@@ -1,5 +1,7 @@
from SuperTagger.SuperTagger.SuperTagger import SuperTagger
from utils import read_supertags_csv, load_obj
+import torch
+torch.cuda.empty_cache()
# region data
file_path = 'SuperTagger/Datasets/m2_dataset_V2.csv'
@@ -16,7 +18,7 @@ tagger = SuperTagger()
tagger.create_new_model(len(index_to_super),'camembert-base',index_to_super)
## If you want to upload a pretrained model
# tagger.load_weights("models/model_check.pt")
-tagger.train(texts, tags, epochs=2, batch_size=16, validation_rate=0.1,
+tagger.train(texts, tags, epochs=40, batch_size=16, validation_rate=0.1,
tensorboard=True, checkpoint=True)
# endregion